policy

HeRD

carosteven · PyTorch

or hover any field below to flag it

Overview

Name
HeRD
Author
carosteven
Framework
PyTorch
License
unknown
Skill type
manipulation
Evidence level
untested
Task description
Official implementation of HeRD (Hierarchical RL-Diffusion Policy), a robot control framework that combines high-level spatial reinforcement learning with low-level diffusion-based trajectory generation for efficient nonprehensile manipulation in cluttered environments.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

0+20 mentioned but not in catalog yet

No robots list HeRD as compatible yet. Know of one? Flag it above.

Compatible environments

0

No environments list HeRD yet.

Datasets that reference this policy

0

No datasets reference HeRD yet.